Skip to main content
Glama

auth_launch_login

Launch a panel-gated browser login station for an identity, assign an egress proxy, and let an operator complete slider/captcha challenges through the embedded noVNC view.

Instructions

Launch a login station for an identity (login-station-console).

Registers/resets the identity as login_required with an egress proxy (auto-assigned, or the operator's explicit proxy:<id>), then launches the station (a headful-browser Job + the panel-gated noVNC observation channel). The login itself happens inside the station: the operator completes slider/captcha in the panel's embedded view at vnc_url (RELATIVE — open it through the panel with your own credential; no token is embedded and the station is reachable only through the panel). Station status then advances launching -> waiting_operator -> completed; see auth_status.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "source": "<source>",
      "account_alias": "<account_alias>"
    },
    "name": "auth_launch_login"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesthe source the identity belongs to.
automationNologin unit's declared level (default "assisted").assisted
egress_refNooptional explicit egress ``proxy:<id>`` (login + crawl both go through it; unknown/retired/other-account refs are refused with status invalid/conflict and no station launches).
account_aliasYesthe account alias in that source's pool.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (which only declare this is not read-only), the description discloses the state mutation ('Registers/resets the identity as login_required'), the egress refusal behavior ('status invalid/conflict and no station launches'), the security model (no token embedded, reachable only through the panel, vnc_url is relative), and the status lifecycle launching -> waiting_operator -> completed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded in the first line, and the remaining sentences carry dense, non-redundant information about station mechanics and the status progression. It is parenthetical-heavy, which slows reading, but no sentence is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be restated, and the description still covers the entire operator workflow and terminal status sequence. For a state-mutating launch tool with four documented parameters, nothing an agent needs to invoke it correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description adds real meaning by explaining that egress is auto-assigned unless the operator passes an explicit 'proxy:<id>', which clarifies what the schema's null default actually does. The 'automation' level and the source/account_alias pairing get no additional interpretation in the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a concrete verb and resource ('Launch a login station for an identity') and explains the underlying mechanics (identity reset to login_required, egress proxy assignment, headful-browser Job plus panel-gated noVNC channel). It does not, however, distinguish this from the sibling 'auth_request_login', so an agent must infer which of the two login entry points to use from names alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is explicit: the operator must complete slider/captcha inside the panel's embedded view, and progress is tracked via 'auth_status'. What is missing is an explicit exclusion or comparison against 'auth_request_login', so the agent gets clear context but no stated condition for choosing between the two.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.